End of training

README.md

@@ -0,0 +1,60 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: eval_cache_hinglish
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/b43qqej3)
+# eval_cache_hinglish
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.3408
+- eval_model_preparation_time: 0.0045
+- eval_cer: 0.2775
+- eval_wer: 0.4149
+- eval_runtime: 141.9071
+- eval_samples_per_second: 18.068
+- eval_steps_per_second: 1.135
+- step: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 300
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 1000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.43.1
+- Pytorch 2.4.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_cer": 0.2775128370109635,
+    "eval_loss": 1.3408493995666504,
+    "eval_model_preparation_time": 0.0045,
+    "eval_runtime": 141.9071,
+    "eval_samples": 2564,
+    "eval_samples_per_second": 18.068,
+    "eval_steps_per_second": 1.135,
+    "eval_wer": 0.4148846278843029
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec_outputs/pd_warmup_500/s300_shuff100",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.3,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.3,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.2,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 148,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 151,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_cer": 0.2775128370109635,
+    "eval_loss": 1.3408493995666504,
+    "eval_model_preparation_time": 0.0045,
+    "eval_runtime": 141.9071,
+    "eval_samples": 2564,
+    "eval_samples_per_second": 18.068,
+    "eval_steps_per_second": 1.135,
+    "eval_wer": 0.4148846278843029
+}

evalonlyhinglish_indicwav2vec_MUCS_warmup2000_s300shuff500_2144487.out

@@ -0,0 +1,308 @@
+wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
+wandb: wandb version 0.17.7 is available!  To upgrade, please run:
+wandb:  $ pip install wandb --upgrade
+wandb: Tracking run with wandb version 0.17.6
+wandb: Run data is saved locally in /scratch/elec/t405-puhe/p/palp3/MUCS/wandb/run-20240822_173605-b43qqej3
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd20000_w500_s300_shuff100_hinglish
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/b43qqej3
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/feature_extraction_auto.py:329: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/accelerate/accelerator.py:488: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
+  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
+max_steps is given, it will override any value given in num_train_epochs
+Wav2Vec2CTCTokenizer(name_or_path='', vocab_size=149, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '[UNK]', 'pad_token': '[PAD]'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
+	147: AddedToken("[UNK]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	148: AddedToken("[PAD]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	149: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	150: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+}
+CHECK MODEL PARAMS Wav2Vec2ForCTC(
+  (wav2vec2): Wav2Vec2Model(
+    (feature_extractor): Wav2Vec2FeatureEncoder(
+      (conv_layers): ModuleList(
+        (0): Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(1, 512, kernel_size=(10,), stride=(5,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+        (1-4): 4 x Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(512, 512, kernel_size=(3,), stride=(2,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+        (5-6): 2 x Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(512, 512, kernel_size=(2,), stride=(2,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+      )
+    )
+    (feature_projection): Wav2Vec2FeatureProjection(
+      (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+      (projection): Linear(in_features=512, out_features=1024, bias=True)
+      (dropout): Dropout(p=0.3, inplace=False)
+    )
+    (encoder): Wav2Vec2EncoderStableLayerNorm(
+      (pos_conv_embed): Wav2Vec2PositionalConvEmbedding(
+        (conv): ParametrizedConv1d(
+          1024, 1024, kernel_size=(128,), stride=(1,), padding=(64,), groups=16
+          (parametrizations): ModuleDict(
+            (weight): ParametrizationList(
+              (0): _WeightNorm()
+            )
+          )
+        )
+        (padding): Wav2Vec2SamePadLayer()
+        (activation): GELUActivation()
+      )
+      (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.2, inplace=False)
+      (layers): ModuleList(
+        (0-23): 24 x Wav2Vec2EncoderLayerStableLayerNorm(
+          (attention): Wav2Vec2SdpaAttention(
+            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          )
+          (dropout): Dropout(p=0.2, inplace=False)
+          (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+          (feed_forward): Wav2Vec2FeedForward(
+            (intermediate_dropout): Dropout(p=0.0, inplace=False)
+            (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True)
+            (intermediate_act_fn): GELUActivation()
+            (output_dense): Linear(in_features=4096, out_features=1024, bias=True)
+            (output_dropout): Dropout(p=0.2, inplace=False)
+          )
+          (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+  )
+  (dropout): Dropout(p=0.0, inplace=False)
+  (lm_head): Linear(in_features=1024, out_features=151, bias=True)
+)
+check the eval set length 2564
+08/22/2024 17:36:18 - INFO - __main__ - *** Evaluate ***
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+
  0%|          | 0/161 [00:00<?, ?it/s]
  1%|          | 2/161 [00:00<01:07,  2.36it/s]
  2%|▏         | 3/161 [00:01<01:28,  1.79it/s]
  2%|▏         | 4/161 [00:02<01:51,  1.40it/s]
  3%|▎         | 5/161 [00:03<02:02,  1.27it/s]
  4%|▎         | 6/161 [00:04<02:07,  1.22it/s]
  4%|▍         | 7/161 [00:05<02:37,  1.02s/it]
  5%|▍         | 8/161 [00:08<03:33,  1.40s/it]
  6%|▌         | 9/161 [00:09<03:53,  1.54s/it]
  6%|▌         | 10/161 [00:10<03:25,  1.36s/it]
  7%|▋         | 11/161 [00:11<02:56,  1.18s/it]
  7%|▋         | 12/161 [00:12<02:30,  1.01s/it]
  8%|▊         | 13/161 [00:13<02:23,  1.03it/s]
  9%|▊         | 14/161 [00:14<02:43,  1.11s/it]
  9%|▉         | 15/161 [00:16<03:00,  1.24s/it]
 10%|▉         | 16/161 [00:17<02:47,  1.16s/it]
 11%|█         | 17/161 [00:17<02:23,  1.00it/s]
 11%|█         | 18/161 [00:18<02:09,  1.11it/s]
 12%|█▏        | 19/161 [00:19<01:59,  1.19it/s]
 12%|█▏        | 20/161 [00:19<01:57,  1.20it/s]
 13%|█▎        | 21/161 [00:20<01:45,  1.32it/s]
 14%|█▎        | 22/161 [00:21<01:51,  1.25it/s]
 14%|█▍        | 23/161 [00:23<02:30,  1.09s/it]
 15%|█▍        | 24/161 [00:24<02:29,  1.09s/it]
 16%|█▌        | 25/161 [00:25<02:20,  1.03s/it]
 16%|█▌        | 26/161 [00:25<02:11,  1.03it/s]
 17%|█▋        | 27/161 [00:26<02:02,  1.10it/s]
 17%|█▋        | 28/161 [00:27<01:54,  1.16it/s]
 18%|█▊        | 29/161 [00:28<01:49,  1.20it/s]
 19%|█▊        | 30/161 [00:28<01:45,  1.24it/s]
 19%|█▉        | 31/161 [00:29<01:36,  1.34it/s]
 20%|█▉        | 32/161 [00:30<01:30,  1.42it/s]
 20%|██        | 33/161 [00:30<01:30,  1.42it/s]
 21%|██        | 34/161 [00:31<01:27,  1.46it/s]
 22%|██▏       | 35/161 [00:32<01:25,  1.48it/s]
 22%|██▏       | 36/161 [00:32<01:22,  1.51it/s]
 23%|██▎       | 37/161 [00:33<01:19,  1.55it/s]
 24%|██▎       | 38/161 [00:34<01:20,  1.52it/s]
 24%|██▍       | 39/161 [00:34<01:24,  1.44it/s]
 25%|██▍       | 40/161 [00:35<01:29,  1.36it/s]
 25%|██▌       | 41/161 [00:36<01:36,  1.24it/s]
 26%|██▌       | 42/161 [00:37<01:40,  1.18it/s]
 27%|██▋       | 43/161 [00:38<01:41,  1.16it/s]
 27%|██▋       | 44/161 [00:39<01:42,  1.15it/s]
 28%|██▊       | 45/161 [00:40<01:34,  1.23it/s]
 29%|██▊       | 46/161 [00:40<01:28,  1.30it/s]
 29%|██▉       | 47/161 [00:41<01:28,  1.29it/s]
 30%|██▉       | 48/161 [00:42<01:28,  1.27it/s]
 30%|███       | 49/161 [00:43<01:27,  1.28it/s]
 31%|███       | 50/161 [00:43<01:28,  1.26it/s]
 32%|███▏      | 51/161 [00:44<01:29,  1.23it/s]
 32%|███▏      | 52/161 [00:45<01:34,  1.15it/s]
 33%|███▎      | 53/161 [00:46<01:36,  1.12it/s]
 34%|███▎      | 54/161 [00:47<01:32,  1.16it/s]
 34%|███▍      | 55/161 [00:48<01:25,  1.24it/s]
 35%|███▍      | 56/161 [00:48<01:18,  1.33it/s]
 35%|███▌      | 57/161 [00:49<01:14,  1.40it/s]
 36%|███▌      | 58/161 [00:50<01:11,  1.45it/s]
 37%|███▋      | 59/161 [00:50<01:07,  1.51it/s]
 37%|███▋      | 60/161 [00:51<01:04,  1.57it/s]
 38%|███▊      | 61/161 [00:52<01:06,  1.50it/s]
 39%|███▊      | 62/161 [00:52<01:07,  1.47it/s]
 39%|███▉      | 63/161 [00:53<01:06,  1.47it/s]
 40%|███▉      | 64/161 [00:54<01:09,  1.39it/s]
 40%|████      | 65/161 [00:55<01:11,  1.35it/s]
 41%|████      | 66/161 [00:55<01:12,  1.31it/s]
 42%|████▏     | 67/161 [00:56<01:12,  1.29it/s]
 42%|████▏     | 68/161 [00:57<01:12,  1.28it/s]
 43%|████▎     | 69/161 [00:58<01:10,  1.30it/s]
 43%|████▎     | 70/161 [00:59<01:12,  1.26it/s]
 44%|████▍     | 71/161 [00:59<01:11,  1.25it/s]
 45%|████▍     | 72/161 [01:00<01:13,  1.20it/s]
 45%|████▌     | 73/161 [01:01<01:13,  1.20it/s]
 46%|████▌     | 74/161 [01:02<01:10,  1.23it/s]
 47%|████▋     | 75/161 [01:02<01:04,  1.34it/s]
 47%|████▋     | 76/161 [01:03<01:03,  1.33it/s]
 48%|████▊     | 77/161 [01:04<01:04,  1.30it/s]
 48%|████▊     | 78/161 [01:05<01:06,  1.25it/s]
 49%|████▉     | 79/161 [01:06<01:06,  1.24it/s]
 50%|████▉     | 80/161 [01:06<01:04,  1.25it/s]
 50%|█████     | 81/161 [01:07<01:03,  1.25it/s]
 51%|█████     | 82/161 [01:08<00:59,  1.33it/s]
 52%|█████▏    | 83/161 [01:08<00:53,  1.47it/s]
 52%|█████▏    | 84/161 [01:09<00:50,  1.53it/s]
 53%|█████▎    | 85/161 [01:10<00:52,  1.44it/s]
 53%|█████▎    | 86/161 [01:11<00:54,  1.38it/s]
 54%|█████▍    | 87/161 [01:12<00:58,  1.26it/s]
 55%|█████▍    | 88/161 [01:13<01:01,  1.18it/s]
 55%|█████▌    | 89/161 [01:13<01:01,  1.17it/s]
 56%|█████▌    | 90/161 [01:14<00:57,  1.23it/s]
 57%|█████▋    | 91/161 [01:15<00:53,  1.31it/s]
 57%|█████▋    | 92/161 [01:15<00:51,  1.35it/s]
 58%|█████▊    | 93/161 [01:16<00:50,  1.34it/s]
 58%|█████▊    | 94/161 [01:17<00:49,  1.36it/s]
 59%|█████▉    | 95/161 [01:18<00:48,  1.37it/s]
 60%|█████▉    | 96/161 [01:18<00:43,  1.49it/s]
 60%|██████    | 97/161 [01:19<00:43,  1.47it/s]
 61%|██████    | 98/161 [01:20<00:42,  1.48it/s]
 61%|██████▏   | 99/161 [01:20<00:41,  1.50it/s]
 62%|██████▏   | 100/161 [01:21<00:41,  1.46it/s]
 63%|██████▎   | 101/161 [01:22<00:39,  1.54it/s]
 63%|██████▎   | 102/161 [01:22<00:39,  1.50it/s]
 64%|██████▍   | 103/161 [01:23<00:39,  1.46it/s]
 65%|██████▍   | 104/161 [01:24<00:42,  1.36it/s]
 65%|██████▌   | 105/161 [01:25<00:41,  1.34it/s]
 66%|██████▌   | 106/161 [01:25<00:38,  1.43it/s]
 66%|██████▋   | 107/161 [01:26<00:36,  1.47it/s]
 67%|██████▋   | 108/161 [01:27<00:37,  1.42it/s]
 68%|██████▊   | 109/161 [01:27<00:36,  1.44it/s]
 68%|██████▊   | 110/161 [01:28<00:35,  1.45it/s]
 69%|██████▉   | 111/161 [01:29<00:35,  1.42it/s]
 70%|██████▉   | 112/161 [01:29<00:34,  1.43it/s]
 70%|███████   | 113/161 [01:30<00:33,  1.45it/s]
 71%|███████   | 114/161 [01:31<00:31,  1.49it/s]
 71%|███████▏  | 115/161 [01:31<00:30,  1.51it/s]
 72%|███████▏  | 116/161 [01:32<00:31,  1.45it/s]
 73%|███████▎  | 117/161 [01:33<00:30,  1.44it/s]
 73%|███████▎  | 118/161 [01:33<00:27,  1.55it/s]
 74%|███████▍  | 119/161 [01:34<00:25,  1.62it/s]
 75%|███████▍  | 120/161 [01:34<00:24,  1.66it/s]
 75%|███████▌  | 121/161 [01:35<00:24,  1.63it/s]
 76%|███████▌  | 122/161 [01:36<00:23,  1.69it/s]
 76%|███████▋  | 123/161 [01:36<00:24,  1.53it/s]
 77%|███████▋  | 124/161 [01:37<00:24,  1.48it/s]
 78%|███████▊  | 125/161 [01:38<00:24,  1.48it/s]
 78%|███████▊  | 126/161 [01:38<00:23,  1.50it/s]
 79%|███████▉  | 127/161 [01:39<00:23,  1.48it/s]
 80%|███████▉  | 128/161 [01:40<00:22,  1.44it/s]
 80%|████████  | 129/161 [01:41<00:25,  1.28it/s]
 81%|████████  | 130/161 [01:42<00:24,  1.27it/s]
 81%|████████▏ | 131/161 [01:42<00:21,  1.40it/s]
 82%|████████▏ | 132/161 [01:43<00:20,  1.43it/s]
 83%|████████▎ | 133/161 [01:43<00:19,  1.47it/s]
 83%|████████▎ | 134/161 [01:44<00:18,  1.43it/s]
 84%|████████▍ | 135/161 [01:45<00:17,  1.49it/s]
 84%|████████▍ | 136/161 [01:45<00:16,  1.49it/s]
 85%|████████▌ | 137/161 [01:46<00:16,  1.45it/s]
 86%|████████▌ | 138/161 [01:47<00:15,  1.48it/s]
 86%|████████▋ | 139/161 [01:47<00:14,  1.52it/s]
 87%|████████▋ | 140/161 [01:48<00:13,  1.51it/s]
 88%|████████▊ | 141/161 [01:49<00:13,  1.45it/s]
 88%|████████▊ | 142/161 [01:50<00:13,  1.44it/s]
 89%|████████▉ | 143/161 [01:50<00:12,  1.47it/s]
 89%|████████▉ | 144/161 [01:51<00:11,  1.46it/s]
 90%|█████████ | 145/161 [01:52<00:10,  1.46it/s]
 91%|█████████ | 146/161 [01:52<00:10,  1.37it/s]
 91%|█████████▏| 147/161 [01:54<00:15,  1.08s/it]
 92%|█████████▏| 148/161 [01:56<00:17,  1.38s/it]
 93%|█████████▎| 149/161 [01:58<00:15,  1.30s/it]
 93%|█████████▎| 150/161 [01:58<00:12,  1.13s/it]
 94%|█████████▍| 151/161 [01:59<00:09,  1.02it/s]
 94%|█████████▍| 152/161 [02:00<00:08,  1.11it/s]
 95%|█████████▌| 153/161 [02:01<00:07,  1.07it/s]
 96%|█████████▌| 154/161 [02:02<00:06,  1.09it/s]
 96%|█████████▋| 155/161 [02:02<00:05,  1.08it/s]
 97%|█████████▋| 156/161 [02:03<00:04,  1.17it/s]
 98%|█████████▊| 157/161 [02:04<00:03,  1.24it/s]
 98%|█████████▊| 158/161 [02:05<00:02,  1.29it/s]
 99%|█████████▉| 159/161 [02:05<00:01,  1.41it/s]
 99%|█████████▉| 160/161 [02:05<00:00,  1.71it/s]
+Printing predictions for a few samples:
+Sample 1:
+  Reference: लिबर ऑफिस impress में एक प्रस्तुति document बनाना और बुनियादी formatting के इस spoken tutorial में आपका स्वागत है
+######
+
+
+  Prediction: liber ऑfis impes में एक प्रस्तुति document बनाना और बुनियादी formating के इस spoken tutorial में आपका स्वागै
+
+
+
+Sample 2:
+  Reference: इस tutorial में हम impress window के भागों के बारे में सीखेंगे और कैसे स्लाइड इन्सर्ट करें और कॉपी करें फॉन्ट तथा फॉन्ट को फॉर्मेट करना सीखेंगे
+######
+
+
+  Prediction: इस tutorial में हम impres window के भागों के बारे में सीखेंगे और कैसे slide insert करें और copyfornt तथा font को format करना सीखेंगे
+
+
+
+Sample 3:
+  Reference: यहाँ हम अपने ऑपरेटिंग सिस्टम के रूप में gnu/linux और लिबरऑफिस वर्जन 334 का उपयोग कर रहे हैं
+######
+
+
+  Prediction: यहाँ हम अपने operating system के रूप में gnu lिnuक और libr ofic version 334 का उपयोग कर रहे हं
+
+
+
+Sample 4:
+  Reference: चलिए अपनी प्रस्तुति प्रेजैटेशन sample impress open करते हैं जिसे पिछले tutorial में बनाया था
+######
+
+
+  Prediction: चलिए अपनी प्रस्तुति sampl impres open करते हैं जिे
+
+
+
+Sample 5:
+  Reference: चलिए देखते हैं कि screen पर क्या क्या है
+######
+
+
+  Prediction: चलिए देखते हैं कि scren पर क्या क्या है
+
+
+
+last Reference string इस mission पर अधिक जानकारी दिए गए लिंक पर उपलब्ध है
+
+
+last prediction string दिए गए link पर उपलब्ध हैspokepentutorialorg mcthpeint
+***** eval metrics *****
+  eval_cer                    =     0.2775
+  eval_loss                   =     1.3408
+  eval_model_preparation_time =     0.0045
+  eval_runtime                = 0:02:21.90
+  eval_samples                =       2564
+  eval_samples_per_second     =     18.068
+  eval_steps_per_second       =      1.135
+  eval_wer                    =     0.4149
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

json/default-1158ece026da9708/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"audio_id": {"dtype": "string", "_type": "Value"}, "audio_paths": {"dtype": "string", "_type": "Value"}, "transcriptions": {"dtype": "string", "_type": "Value"}}, "builder_name": "json", "dataset_name": "json", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 631424, "num_examples": 2564, "dataset_name": "json"}}, "download_checksums": {"/m/triton/scratch/elec/puhe/p/palp3/MUCS/mucs_language_segregated_data/MUCS_test_languagesep_data.json": {"num_bytes": 1275544, "checksum": null}}, "download_size": 1275544, "dataset_size": 631424, "size_in_bytes": 1906968}

json/default-1158ece026da9708/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/json-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d5b20df5f5f6550555e73f7655a68afc89e2091644cd26c204f08f4c1dd401
+size 632904

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08de7da709cb1c87182ea525062fcd525beeade5ce32613467ec0bcc59e40f04
+size 1262426580

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3168320547d20d2b8c475e7ef20fae9bf5e7d4a6d67d69d3545e10ff1d5e0db
+size 5432